LV-BLiF: Harnessing Language-Vision Representation Learning for Blind Light Field Image Quality Assessment
IEEE Transactions on Broadcasting · 2026-09 · 72 (3) · 960-974
DOI: 10.1109/tbc.2026.3668512 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Broadcasting, 2026-09. Verfasst von Xin Liao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Natural Science Foundation of China, ”Leading Goose” Research and Development Program of Zhejiang Province.
Abstract (Originalsprache)
Light Field Images (LFIs) capture both angular and spatial information, enabling immersive visual experiences for observers. However, during acquisition and processing, LFIs often suffer from various degradations, accompanied by intricate spatio-angular distortions. Consequently, objective LFI Quality Assessment (LFIQA) has garnered significant research interest. Existing blind LFIQA methods predominantly operate in a content-agnostic manner. They primarily model low-level distortions while neglecting the semantic context, a limitation that significantly diverges from the perception mechanisms of the Human Visual System (HVS). To bridge the gap between artifact analysis and scene understanding, we propose LV-BLiF, a novel dual-branch LFIQA network based on language-vision representation learning. Firstly, the textual prompts-assisted branch utilizes a pre-trained quality-aware Large Multimodal Model (LMM) to extract deep semantic representations, which are transformed into semantic context vectors sensitive to spatial-angular quality variations via pseudo-label guided learning strategy. Subsequently, semantic quality scores are generated based on this high-level information. Secondly, the visual cues-assisted branch employs disentangling convolutions to decompose light field features into spatial, angular, and epipolar plane image subspaces. These features are processed by Light Field Residual Blocks (LFRBs) and adaptively integrated via a Mixture-of-Experts-like (MoE-like) gating mechanism to predict visual quality scores. Finally, the semantic and visual scores are fused through a learnable adaptive gating mechanism to derive the overall LFI quality score. Extensive experiments on benchmark datasets, including NBU, SHU, and Win5-LID, demonstrate that LV-BLiF significantly outperforms state-of-the-art methods and exhibits high consistency with human perception. The proposed metric will be publicly available at https://github.com/shuaibilx/LV-BLiF
Förderung
- Natural Science Foundation of China
- ”Leading Goose” Research and Development Program of Zhejiang Province
Zitieren
APA
Liao, X., Chai, X., Chen, H., Jing, W., Shao, F., & Jiang, Q. (2026). LV-BLiF: Harnessing Language-Vision Representation Learning for Blind Light Field Image Quality Assessment. IEEE Transactions on Broadcasting, 72(3), 960-974. https://doi.org/10.1109/tbc.2026.3668512
Vancouver
Liao X, Chai X, Chen H, Jing W, Shao F, Jiang Q. LV-BLiF: Harnessing Language-Vision Representation Learning for Blind Light Field Image Quality Assessment. IEEE Transactions on Broadcasting. 2026;72(3):960-974. doi:10.1109/tbc.2026.3668512
BibTeX
@article{Liao2026,
author = {Liao, Xin and Chai, Xiongli and Chen, Hangwei and Jing, Weiyi and Shao, Feng and Jiang, Qiuping},
title = {LV-BLiF: Harnessing Language-Vision Representation Learning for Blind Light Field Image Quality Assessment},
journal = {IEEE Transactions on Broadcasting},
year = {2026},
volume = {72},
number = {3},
pages = {960--974},
doi = {10.1109/tbc.2026.3668512}
}
EUVIMED